Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.
Identifying and Mitigating the Security Risks of Generative AI, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
A framework with seven dimensions for AI incident reporting systems is developed from literature and case studies in safety-critical industries to guide institutional design choices.
citing papers explorer
-
What makes a harness a harness: necessary and sufficient conditions for an agent harness
Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.
-
Designing Incident Reporting Systems for Harms from General-Purpose AI
A framework with seven dimensions for AI incident reporting systems is developed from literature and case studies in safety-critical industries to guide institutional design choices.